Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1520 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1177. Min Range: -1.1177

Max Act: 1.1177. Min Act: -0.0000

Data Index: 725601 (The Pile)

Max Activating Token Index: 133

Text #1

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.8595. Min Act: -0.0000

Data Index: 488356 (The Pile)

Max Activating Token Index: 47

Text #2

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1527624 (The Pile)

Max Activating Token Index: 556

Text #3

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.8242. Min Act: -0.0000

Data Index: 827721 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.8157. Min Act: -0.0000

Data Index: 526325 (The Pile)

Max Activating Token Index: 250

Text #5

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1064908 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.7368. Min Act: -0.0000

Data Index: 178946 (The Pile)

Max Activating Token Index: 127

Text #7

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1913003 (The Pile)

Max Activating Token Index: 724

Text #8

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.7617. Min Act: -0.0000

Data Index: 1364982 (The Pile)

Max Activating Token Index: 977

Text #9

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1861634 (The Pile)

Max Activating Token Index: 832

Text #10

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1790210 (The Pile)

Max Activating Token Index: 23

Text #11

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1375681 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1447470 (The Pile)

Max Activating Token Index: 41

Text #13

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1173054 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1489942 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.7076. Min Act: -0.0000

Data Index: 843496 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1008118 (The Pile)

Max Activating Token Index: 138

Text #17

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.7114. Min Act: -0.0000

Data Index: 866837 (The Pile)

Max Activating Token Index: 778

Text #18

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1089828 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 1.1177. Min Range: -1.1177

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1803473 (The Pile)

Max Activating Token Index: 923